Denoising Heat-inspired Diffusion with Insulators for Collision Free Motion Planning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chang, Junwoo, Ryu, Hyunwoo, Kim, Jiwoo, Yoo, Soochul, Choi, Jongeun, Seo, Joohwan, Prakash, Nikhil, Horowitz, Roberto
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914673219076096
author Chang, Junwoo
Ryu, Hyunwoo
Kim, Jiwoo
Yoo, Soochul
Choi, Jongeun
Seo, Joohwan
Prakash, Nikhil
Horowitz, Roberto
author_facet Chang, Junwoo
Ryu, Hyunwoo
Kim, Jiwoo
Yoo, Soochul
Choi, Jongeun
Seo, Joohwan
Prakash, Nikhil
Horowitz, Roberto
contents Diffusion models have risen as a powerful tool in robotics due to their flexibility and multi-modality. While some of these methods effectively address complex problems, they often depend heavily on inference-time obstacle detection and require additional equipment. Addressing these challenges, we present a method that, during inference time, simultaneously generates only reachable goals and plans motions that avoid obstacles, all from a single visual input. Central to our approach is the novel use of a collision-avoiding diffusion kernel for training. Through evaluations against behavior-cloning and classical diffusion models, our framework has proven its robustness. It is particularly effective in multi-modal environments, navigating toward goals and avoiding unreachable ones blocked by obstacles, while ensuring collision avoidance. Project Website: https://sites.google.com/view/denoising-heat-inspired
format Preprint
id arxiv_https___arxiv_org_abs_2310_12609
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Denoising Heat-inspired Diffusion with Insulators for Collision Free Motion Planning
Chang, Junwoo
Ryu, Hyunwoo
Kim, Jiwoo
Yoo, Soochul
Choi, Jongeun
Seo, Joohwan
Prakash, Nikhil
Horowitz, Roberto
Robotics
Artificial Intelligence
Machine Learning
Diffusion models have risen as a powerful tool in robotics due to their flexibility and multi-modality. While some of these methods effectively address complex problems, they often depend heavily on inference-time obstacle detection and require additional equipment. Addressing these challenges, we present a method that, during inference time, simultaneously generates only reachable goals and plans motions that avoid obstacles, all from a single visual input. Central to our approach is the novel use of a collision-avoiding diffusion kernel for training. Through evaluations against behavior-cloning and classical diffusion models, our framework has proven its robustness. It is particularly effective in multi-modal environments, navigating toward goals and avoiding unreachable ones blocked by obstacles, while ensuring collision avoidance. Project Website: https://sites.google.com/view/denoising-heat-inspired
title Denoising Heat-inspired Diffusion with Insulators for Collision Free Motion Planning
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2310.12609